NC Bench
Overview
About
Tests
Categories
Models
Vendors
Compare
Run: 2025-11-18-01KACPCZKHQRQ8K1Y25M8RQHS4
Run Details
Model:
Gemini 2.5 Pro
Test:
Dialogue tags
Scenario:
Write unattributed dialogue
Duration:
16.5s
Cost:
$0.016095
Provider:
Google AI Studio
Evaluation summary
Score
Evaluator
Details Link
100.00%
Count dialogue tags
(details)
Model input
User/Human
You are an expert novel writer in the cozy mystery genre. Write a scene of about 200 words, with dialogue between two characters. The dialogue should be unattributed, meaning the speaker is not explicitly mentioned. The scene should be set in a small town bakery. Only return the story, nothing else.
Model response
Messages
Meta
AI
The bell above the door chimed, a cheerful, tinkling sound at odds with the solemn hush inside The Daily Knead. Sunlight streamed through the front window, illuminating dust motes dancing over a half-eaten cherry Danish. “Four lumps. Can you believe it? The man treated his tea like syrup.” “He had a sweet tooth. There’s no crime in that.” “Perhaps not. But there’s something unsettling about a man so particular about his sugar intake turning up face-down in his own prize-winning petunias.” “It was his heart, Florence. The doctor said so.” “The doctor also said Mildred Peabody’s prize-winning poodle had a simple cold, and two days later it was gone. I’m just saying, it’s a curious coincidence.” “What is?” “That the day after Arthur Hemlock finalized his will, leaving everything to a cat sanctuary in Dorset, his heart simply… gives out. And right next to the new weed killer he’d just bought, mind you.” “You think someone poisoned him with weed killer?” “I think it’s a terrible waste of a perfectly good scone. Are you going to finish that?”
created_at
"2025-11-18T23:57:19.493069+00:00"
11/18/2025, 11:57:19 PM
model
"google/gemini-2.5-pro"
app_id
182717
external_user
(null)
streamed
true
cancelled
false
latency
2303
moderation_latency
(null)
generation_time
16393
tokens_prompt
68
tokens_completion
770
native_tokens_prompt
68
native_tokens_completion
1601
native_tokens_completion_images
0
native_tokens_reasoning
1349
native_tokens_cached
0
num_media_prompt
(null)
num_input_audio_prompt
(null)
num_media_completion
0
num_search_results
(null)
origin
"https://ncbench.com/"
is_byok
false
finish_reason
"stop"
native_finish_reason
"STOP"
usage
0.016095
api_type
"completions"
id
"gen-1763510222-797qvQc031eFI5WVMPvp"
upstream_id
(null)
total_cost
0.016095
cache_discount
(null)
upstream_inference_cost
0
provider_name
"Google AI Studio"
Evaluation details
Result
Evaluator
Details
Meta Data
100.00%
Count dialogue tags
n/a
neededClean
false
dialogueTags
(empty)